82 lines
2.8 KiB
Markdown
82 lines
2.8 KiB
Markdown
---
|
|
library_name: transformers
|
|
license: llama3.2
|
|
base_model: meta-llama/Llama-3.2-1B-Instruct
|
|
tags:
|
|
- peft-factory
|
|
- full
|
|
- llama-factory
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: train_rte_42_1776331559
|
|
results: []
|
|
---
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
should probably proofread and complete it, then remove this comment. -->
|
|
|
|
# train_rte_42_1776331559
|
|
|
|
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the rte dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.1189
|
|
- Num Input Tokens Seen: 2035272
|
|
|
|
## Model description
|
|
|
|
More information needed
|
|
|
|
## Intended uses & limitations
|
|
|
|
More information needed
|
|
|
|
## Training and evaluation data
|
|
|
|
More information needed
|
|
|
|
## Training procedure
|
|
|
|
### Training hyperparameters
|
|
|
|
The following hyperparameters were used during training:
|
|
- learning_rate: 5e-06
|
|
- train_batch_size: 8
|
|
- eval_batch_size: 8
|
|
- seed: 42
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
- lr_scheduler_type: cosine
|
|
- lr_scheduler_warmup_ratio: 0.1
|
|
- num_epochs: 5
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|
|
|:-------------:|:------:|:----:|:---------------:|:-----------------:|
|
|
| 0.2309 | 0.2527 | 71 | 0.1802 | 105024 |
|
|
| 0.1861 | 0.5053 | 142 | 0.2462 | 209536 |
|
|
| 0.0658 | 0.7580 | 213 | 0.1589 | 312576 |
|
|
| 0.0765 | 1.0107 | 284 | 0.1189 | 414040 |
|
|
| 0.1848 | 1.2633 | 355 | 0.2128 | 517656 |
|
|
| 0.0306 | 1.5160 | 426 | 0.1791 | 624344 |
|
|
| 0.1029 | 1.7687 | 497 | 0.1360 | 725656 |
|
|
| 0.1868 | 2.0214 | 568 | 0.1606 | 821416 |
|
|
| 0.0259 | 2.2740 | 639 | 0.2542 | 926760 |
|
|
| 0.029 | 2.5267 | 710 | 0.2361 | 1025320 |
|
|
| 0.0005 | 2.7794 | 781 | 0.2352 | 1128104 |
|
|
| 0.0001 | 3.0320 | 852 | 0.2580 | 1229440 |
|
|
| 0.0001 | 3.2847 | 923 | 0.2295 | 1332544 |
|
|
| 0.0001 | 3.5374 | 994 | 0.2405 | 1438336 |
|
|
| 0.0 | 3.7900 | 1065 | 0.2512 | 1539072 |
|
|
| 0.0 | 4.0427 | 1136 | 0.2552 | 1642696 |
|
|
| 0.0 | 4.2954 | 1207 | 0.2572 | 1743624 |
|
|
| 0.0 | 4.5480 | 1278 | 0.2590 | 1849416 |
|
|
| 0.0 | 4.8007 | 1349 | 0.2602 | 1954568 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.51.3
|
|
- Pytorch 2.10.0+cu128
|
|
- Datasets 4.0.0
|
|
- Tokenizers 0.21.4
|